{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/searching-efficient-3d-architectures-with","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","arxiv_id":"2007.16100","date":"2020-07-31","proceeding":"ECCV 2020 8","authors":["Haotian Tang","Zhijian Liu","Shengyu Zhao","Yujun Lin","Ji Lin","Hanrui Wang","Song Han"],"abstract":"Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely. Given the limited hardware resources, existing 3D perception models are not able to recognize small instances (e.g., pedestrians, cyclists) very well due to the low-resolution voxelization and aggressive downsampling. To this end, we propose Sparse Point-Voxel Convolution (SPVConv), a lightweight 3D module that equips the vanilla Sparse Convolution with the high-resolution point-based branch. With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes. To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network architecture over this diverse design space efficiently and effectively. Experimental results validate that the resulting SPVNAS model is fast and accurate: it outperforms the state-of-the-art MinkowskiNet by 3.3%, ranking 1st on the competitive SemanticKITTI leaderboard. It also achieves 8x computation reduction and 3x measured speedup over MinkowskiNet with higher accuracy. Finally, we transfer our method to 3D object detection, and it achieves consistent improvements over the one-stage detection baseline on KITTI.","url_abs":"https://arxiv.org/abs/2007.16100v2","url_pdf":"https://arxiv.org/pdf/2007.16100v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/mit-han-lab/spvnas","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/chenfengxu714/image2point","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/mit-han-lab/torchsparse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/pjlab-adg/openpcseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/pjlab-adg/pcseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"searching-efficient-3d-architectures-with","repo_url":"https://github.com/Pointcept/Pointcept","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"robust-3d-semantic-segmentation","task_name":"Robust 3D Semantic Segmentation"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"SPVNAS","rank_in_archive_order":14,"of":45,"metrics":{"test mIoU":"66.4%","val mIoU":"64.7%"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-wildscenes","task":"3D Semantic Segmentation","dataset":"WildScenes","model":"SPVCNN","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"36.78"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"SPVCNN++","rank_in_archive_order":6,"of":36,"metrics":{"test mIoU":"0.811"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"SPVNAS","rank_in_archive_order":16,"of":36,"metrics":{"test mIoU":"0.77"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on","task":"Robust 3D Semantic Segmentation","dataset":"SemanticKITTI-C","model":"SPVCNN-34","rank_in_archive_order":1,"of":22,"metrics":{"mean Corruption Error (mCE)":"99.16%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on","task":"Robust 3D Semantic Segmentation","dataset":"SemanticKITTI-C","model":"SPVCNN-18","rank_in_archive_order":4,"of":22,"metrics":{"mean Corruption Error (mCE)":"100.30%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on-wod-c","task":"Robust 3D Semantic Segmentation","dataset":"WOD-C","model":"SPVCNN-34","rank_in_archive_order":2,"of":5,"metrics":{"mean Corruption Error (mCE)":"98.72%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on-wod-c","task":"Robust 3D Semantic Segmentation","dataset":"WOD-C","model":"SPVCNN-18","rank_in_archive_order":4,"of":5,"metrics":{"mean Corruption Error (mCE)":"103.60%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on-nuscenes-c","task":"Robust 3D Semantic Segmentation","dataset":"nuScenes-C","model":"SPVCNN-34","rank_in_archive_order":3,"of":12,"metrics":{"mean Corruption Error (mCE)":"97.45%"},"uses_additional_data":false},{"leaderboard":"/sota/robust-3d-semantic-segmentation-on-nuscenes-c","task":"Robust 3D Semantic Segmentation","dataset":"nuScenes-C","model":"SPVCNN-18","rank_in_archive_order":7,"of":12,"metrics":{"mean Corruption Error (mCE)":"106.65%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.16100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.16100"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/torchsparse","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chenfengxu714/image2point","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pjlab-adg/openpcseg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pjlab-adg/pcseg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pointcept/Pointcept","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/spvnas","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"0b71a9bb5beea7b9","entry":"create_label_map","repo":"mit-han-lab/spvnas","repo_kind":"official","path":"visualize.py","file_url":"https://github.com/mit-han-lab/spvnas/blob/HEAD/visualize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b71a9bb5beea7b9"}},{"code_sha256_prefix":"82545d97082ff5f4","entry":"download_url","repo":"mit-han-lab/spvnas","repo_kind":"official","path":"model_zoo.py","file_url":"https://github.com/mit-han-lab/spvnas/blob/HEAD/model_zoo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82545d97082ff5f4"}},{"code_sha256_prefix":"5353e04b2b5c5a26","entry":"make_divisible","repo":"mit-han-lab/spvnas","repo_kind":"official","path":"core/modules/dynamic_sparseop.py","file_url":"https://github.com/mit-han-lab/spvnas/blob/HEAD/core/modules/dynamic_sparseop.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5353e04b2b5c5a26"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}